recommend_skills

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint/idempotent/non-destructive, yet the description adds the critical clarification that the tool stays read-only 'even when dry_run=false' — the exact misreading an agent would otherwise make. It further discloses the evidence basis (recurrence plus nonempty curated evidence entries, duplicate summaries counted separately, not facts/logs/transcripts) and tells the agent to inspect returned thresholds and limitations first.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the action and routing advice, and every sentence carries information. The read-only denial list ('promote, import, synchronize, create, or mutate') and the threshold sentence are dense and slightly repetitive with the schema, but the redundancy is defensible for a guardrail statement.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers prerequisites, read-only guarantees, evidence sourcing, and hand-off to downstream tools; the return contents are summarized even though an output schema exists. For a three-parameter read tool in a large sibling set, nothing an agent needs before calling is absent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds real meaning: it clarifies that dry_run=false does not enable writes and that evidence is counted from curated entries rather than fact/log scans. It does not restate the scope enum values beyond the prerequisite note, but nothing material is missing.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Review latent workflow recommendations') plus the exact evidence source ('explicit track_latent_skill evidence'). It also names the sibling it is not ('use list_skills for the full catalog'), so an agent can route correctly without opening a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly says when to use it ('choose candidates for proposal or promotion'), names the alternative for a different need (list_skills), and points to the downstream tools (propose_skill, promote_skill_recommendation) that consume the output. The prerequisite ('Project/all scope requires initialized project memory') is also stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.